Senior Machine Learning Engineer - 3D Reconstruction
Torc RoboticsVisit Torc Robotics website
Torc Robotics is a Daimler Truck subsidiary developing Level 4 autonomous-driving software and systems for long-haul Freightliner Cascadia trucks.
Blacksburg, United States
About Torc Robotics
Founded in 2005 as Torc Technologies, Torc Robotics commercializes self-driving trucking technology, including its virtual-driver software, for freight operations.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design, implement, and deploy offline 3D reconstruction, lane-line detection, mapping, and pose-correction systems. You will train models, improve data and annotation quality, set technical direction, and mentor engineers working on high-complexity projects.
Requirements
- Lane-line detection, network reconstruction, and lane-line model training experience.
- Experience creating lane-line maps and managing map updates.
- Pose correction and calibration-error diagnosis across camera, lidar, radar, and GPS/IMU systems.
- Advanced computer vision, deep learning, active learning, and pseudo-labeling knowledge.
- Deep expertise in at least two of 2D/3D object detection, tracking, sensor fusion, semantic segmentation, SLAM, and BEV.
- MLOps, experiment tracking, model registries, MLflow, Weights & Biases, and model evaluation experience.
- Experience with PyTorch, Lightning, or Ray.
- Parquet data processing using PyArrow, Daft, or Pandas.
- Advanced Python development, cloud development environments, GitHub Actions, and Docker.
- Bachelor's degree plus 6+ years, master's degree plus 3+ years, or PhD plus 1+ years of relevant experience.
Responsibilities
- Design, implement, and deploy offline 3D reconstruction, lane-line detection, and automatic mapping systems.
- Lead lane-line network reconstruction and create topologically correct lane-line graphs.
- Train and improve lane-line detection and creation models.
- Create lane-line maps for unmapped areas and propagate map updates.
- Correct sensor poses and diagnose calibration and sensor errors.
- Set technical direction for lane-line, mapping, and pose-estimation pipelines.
- Lead high-complexity projects and mentor engineers.
- Develop perception and mapping algorithms using disciplined software practices.
- Implement data ingestion, preparation, curation, and governance workflows.
- Measure auto-labeling and map-creation quality.
Benefits
- Bonus component and stock options.
- 100% paid medical, dental, and vision premiums for full-time employees.
- 401K plan with a 6% employer match.
- Flexible schedule and generous paid vacation available immediately after start date.
- AD+D and life insurance.